© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14483
    Prev
    Next
    INDEX
    Explanations

    doomed, destined, fate, inevitable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĻİ
    -0.21
    è¿ĩå¾Ĺ
    -0.21
    Sn
    -0.19
     Spicer
    -0.19
    秦
    -0.19
     Elev
    -0.18
    attach
    -0.18
    å¹´é¾Ħ
    -0.18
     Exterior
    -0.17
    ä¸Ĭå²Ĺ
    -0.17
    POSITIVE LOGITS
    注å®ļ
    0.26
     destined
    0.26
     doomed
    0.26
     already
    0.25
     inev
    0.25
    ä¸įåı¯éģ¿åħį
    0.23
    èĤ¯å®ļä¼ļ
    0.22
    already
    0.22
    committed
    0.22
    æĹ©æĹ©
    0.22
    Activations Density 0.150%

    No Known Activations